Sparse hidden Markov models for purer clusters

Sujeeth Bharadwaj, Mark Hasegawa-Johnson, Jitendra Ajmera, Om Deshmukh, Ashish Verma

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

The hidden Markov model (HMM) is widely popular as the de facto tool for representing temporal data; in this paper, we add to its utility in the sequence clustering domain - we describe a novel approach that allows us to directly control purity in HMM-based clustering algorithms. We show that encouraging sparsity in the observation probabilities increases cluster purity and derive an algorithm based on lp regularization; as a corollary, we also provide a different and useful interpretation of the value of p in Renyi p-entropy. We test our method on the problem of clustering non-speech audio events from the BBC sound effects corpus. Experimental results confirm that our approach does learn purer clusters, with (unweighted) average purity as high as 0.88 - a considerable improvement over both the baseline HMM (0.72) and k-means clustering (0.69).

Original languageEnglish (US)
Title of host publication2013 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Proceedings
Pages3098-3102
Number of pages5
DOIs
StatePublished - Oct 18 2013
Event2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013 - Vancouver, BC, Canada
Duration: May 26 2013May 31 2013

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
ISSN (Print)1520-6149

Other

Other2013 38th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2013
Country/TerritoryCanada
CityVancouver, BC
Period5/26/135/31/13

Keywords

  • Renyi entropy
  • cluster purity
  • hidden Markov model
  • sequence clustering
  • sparsity

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Fingerprint

Dive into the research topics of 'Sparse hidden Markov models for purer clusters'. Together they form a unique fingerprint.

Cite this